Subject Guides: Digital Humanities: Data and Text Mining

Data and Text Mining

What is text and data mining?

Text and data mining (TDM) are often used together although they are slightly different. Both use computational analysis of vast quantities of digital information. However text mining looks more at natural language text and data mining at structured data.

Researchers use specialized tools to extract data, identify trends, look for patterns and better understand the relationships of terms within and between documents. Analysis might focus on word frequency, words that frequently appear near each other, contextual information for key words, common phrases and other patterns.

Analyzes can happen from websites (such as publicly available Facebook posts), to 16th C. manuscripts, to DNA sequences, as well as old newspapers

UAlberta Library databases that allow some mining

These resources allow for some kind of mining. Please contact a subject librarian for more details and to investigate options (and they can contact our licensing department ). Note: many databases do not allow TDM, or have quite limited options, without individual agreements with the company and possible extra fees.

Early English Books Online This link opens in a new window
- This link opens in a new window
- This link opens in a new window
AKA EEBO. Page images of virtually every work printed in England, Ireland, Scotland, Wales and British North America, and others between 1473 and 1700. Many converted to plain text (TCP) that can be downloaded as pdf or txt files individually or as a folder group.
Eighteenth Century Collections Online This link opens in a new window
- This link opens in a new window
- This link opens in a new window
AKA Gale 18th Century Collections Online. Search/display/download digital images and/or OCR text of books, pamphlets, and broadsides published during the 18th Century. note: OCR accuracy is quite low.

Evans Texts - Text Creation Partnership with EEBO, ECCO and EVANS Books, pamphlets, and broadsides published during the 17th and 18th centuries.

Gale Primary Sources This link opens in a new window An integrated research platform that allows searching across Gale primary source collections.
- This link opens in a new window
- This link opens in a new window
JSTOR This link opens in a new window JSTOR contains fulltext academic journals in the Humanities, Social Sciences, and Sciences. JSTOR provides complete journal backruns from the date of initial publication up to a date defined, on a publisher by publisher basis, by a "moving wall". The moving wall is a fixed period of time ranging, in most cases, from 2 to 5 years, that defines the gap between the most recently published issue and the date of the most recent issues available in JSTOR.
- This link opens in a new window
- This link opens in a new window
Lexis+ Academic Premium This link opens in a new window This database contains up to date Canadian Case Law and Legislation including expert Commentary, Current awareness, Legal Encyclopedias, Law Journals & Reviews, Practical Guidance, and Data-driven Insights. [Previously Lexis Advance Quicklaw]
- This link opens in a new window
- This link opens in a new window
Readex AllSearch This link opens in a new window Readex AllSearch is an integrated research platform that allows searching across Readex collections.
- This link opens in a new window
- This link opens in a new window
SAGE Journals This link opens in a new window This site brings access to over a thousand peer-reviewed journals, spanning humanities, social sciences and science, technology, engineering and medicine. There are also journals relating to business, special education, sociology, and urban studies.
- This link opens in a new window
- This link opens in a new window

Science Direct You may use this platform to text mine Elsevier products to which the library subscribes.
University of California Press Text mining is approved for authorized users for academic purposes.

Wiley Online Library This link opens in a new window Also known as: |Wiley Interscience|Blackwell Journals| Provides access to the fulltext of journals and selected e-books from John Wiley & Sons. Includes titles in AnthroSource.
- This link opens in a new window
- This link opens in a new window

Electronic Text Centers

Center for Electronic Texts
Electronic Text Center UVirginia combines an on-line archive of thousands of SGML-encoded electronic texts (some of which are publicly available) with a library-based Center housing hardware and software suitable for the creation and analysis of text.
Electronic Text Service At Columbia University.
LETRS: Library Electronic Texts Resource Service
The Survey of English Usage

Free Sources: Open access databases and repositories used for text and data mining

arXiv.org From Cornell University. Open access to 1,153,908 e-prints in Physics, Mathematics, Computer Science, Quantitative Biology, Quantitative Finance and Statistics.
BioMed Central From Springer Science+Business Media. Over 250,000 full-text, peer-reviewed articles are available for text and data mining.
Chronicling America: Historical American Newspapers From Library of Congress. Collection of digitized historical newspapers from 1836-1922. OCR batch downloads.
Corpus.byu.edu From Brigham Young University. Compiled by Prof. Mark Davies, Linguistics, at Brigham Young University, there are multiple corpora available for analysis, for English, as well as Spanish and Portuguese.
Digital Public Library of America From DPLA. Data is available for bulk download in JSON files. More information about the Database export files.
Google Books From Google. Ngram Viewer: from 1800 to 2000.
HathiTrust Digital Library Covers all subjects, including thousands of mathematics titles. HathiTrust is a collective digital repository for several research libraries. Some works in the public domain; others have restricted access due to copyright.
Internet Archive & Open Library From: Internet Archive. Offers over 10,000,000 fully accessible books and texts.
MSU Libraries Humanities Data From Michigan State University. Includes but is not limited to digitized and born digital text, audio, images, moving images, and the metadata that describes them, with particular strength in text and audio data.
PLOS From Public Library of Science. Provides access to its peer-reviewed articles.
Project Gutenberg From Project Gutenberg. The first producer of free electronic books (ebooks), their catalog includes nearly 30,000 free books and over 100,000 titles.
PubMed Central : Databases and Text Mining Tools From NCBI. Multiple text mining tools to analyze not only scholarly publications, but also other types of biomedical resources, such as Electronic Health Records.
University of Oxford Text Archive From University of Oxford. A repository of digital literary and linguistic resources for research and teaching in higher education.

Text Collections

Aboriginal & Tooes Strait Islander Data Archive
Alex: A Catalog of Electronic Texts
ALMA E-Books From the African Language Materials Archive (ALMA) program, a cooperative project of the Digital Library for International Research and the West African Research Association.
AMALGAM Automatic Mapping Among Lexico-Grammatical Annotation Models
ARTFL Project University of Chicago, Project for American and French Research on the Treasury of the French Language
CELT: Corpus of Electronic Texts Contemporary and historical Irish documents.
Corpus Bambara de Reference A massive corpus of annotated texts in the Bambara language.
Corpus Cyrillo-Methodianum Helsingiense An electronic corpus of Old Church Slavonic texts.
Corpus Maninka de Reference A collection of annotated texts in the Maninka language of Guinea (also see Maninka below).
The First World War Poetry Digital Archive
Goteborg Language Bank of Swedish
International Corpus of English
IPL Reading Room Public Online Texts
Japanese Text Initiative
The Labyrinth (Georgetown medieval studies).
Linguistic Data Consortium
Maninka Maninka language of Guinea corpus (Cyrillic alphabet).
Online Books Page
Online Books - FAQ
Oxford Text Archive (OTA)
Penn Corpora of Historical English A database of 510,000 words of syntactically parsed Middle English text for use by historical linguists.
Perseus Digital Library Classical Greek texts both in Greek and in English translation.
Philosophy Etexts
Project Libellus (Classics)
Spanish corpora
UMich Humanities Text Initiative

Digital Humanities